A Deep Residual U-Net Algorithm for Automatic Detection and Quantification of Ascites on Abdominopelvic Computed Tomography Images Acquired in the Emergency Department: Model Development and Validation

Abstract

Background Detection and quantification of intra-abdominal free fluid (ie, ascites) on computed tomography (CT) images are essential processes for finding emergent or urgent conditions in patients. In an emergency department, automatic detection and quantification of ascites will be beneficial. Objective We aimed to develop an artificial intelligence (AI) algorithm for the automatic detection and quantification of ascites simultaneously using a single deep learning model (DLM). Methods We developed 2D DLMs based on deep residual U-Net, U-Net, bidirectional U-Net, and recurrent residual U-Net (R2U-Net) algorithms to segment areas of ascites on abdominopelvic CT images. Based on segmentation results, the DLMs detected ascites by classifying CT images into ascites images and nonascites images. The AI algorithms were trained using 6337 CT images from 160 subjects (80 with ascites and 80 without ascites) and tested using 1635 CT images from 40 subjects (20 with ascites and 20 without ascites). The performance of the AI algorithms was evaluated for diagnostic accuracy of ascites detection and for segmentation accuracy of ascites areas. Of these DLMs, we proposed an AI algorithm with the best performance. Results The segmentation accuracy was the highest for the deep residual U-Net model with a mean intersection over union (mIoU) value of 0.87, followed by U-Net, bidirectional U-Net, and R2U-Net models (mIoU values of 0.80, 0.77, and 0.67, respectively). The detection accuracy was the highest for the deep residual U-Net model (0.96), followed by U-Net, bidirectional U-Net, and R2U-Net models (0.90, 0.88, and 0.82, respectively). The deep residual U-Net model also achieved high sensitivity (0.96) and high specificity (0.96). Conclusions We propose a deep residual U-Net–based AI algorithm for automatic detection and quantification of ascites on abdominopelvic CT scans, which provides excellent performance.

Applying artificial intelligence to detect and analyse oral and maxillofacial bone loss—A scoping review

“…Refers to the simulation of human intelligence in machines that are programmed to think like humans and mimic their actions [18] -Algorithm A formula or set of rules (or procedure, processes, instructions or steps) for solving a problem or for performing a task. In Artificial Intelligence, the algorithm tells the machine how to find answers to a question or solutions to a problem [19] ML Machine learning Aims to equip computers with knowledge from data and observations rather than expressly programming them [10] ANN Artificial neural network An artificial neural network (or simply neural network) consists of an input layer of neurons (or nodes, units), one or two (or even three) hidden layers of neurons and a final layer of output neurons [20] Resnet The key components of this method are the regional proposal network, the core idea of which is to densely sample the entire input image through overlapping bounding boxes of many different shapes and sizes and then train the network to generate multiple object proposals (also known as 'Region of Interest' [ROI]) [24] -Faster R-CNN Further refines and classifies ROI through an additional fully connected layer based on a regional proposal network [24] -Mask R-CNN Further improves Faster R-CNN using an additional convolutional layer instance segmentation in the ROI [24] U-NET U-net convolutional neural network U-Net is one of the deep learning networks with an encoder-decoder architecture, which employs skip connections to combine low-level feature maps from an encoder and high-level semantic feature maps from a decoder [25] YOLO-V4 You look only once neural network technology YOLO-v4 is a high-precision and real-time One-Stage object detection algorithm based on regression, which integrated the characteristics of YOLO-v1, YOLO-v2, YOLO-v3, etc. and achieved the current optimum in terms of detection speed and trade-off of detection accuracy.…”

Body location embedded 3D U-Net (BLE-U-Net) for ovarian cancer ascites segmentation on CT scans

“…A 2D residual U-Net was used to detect and segment ascites on individual CT slice. 5 Segmentation artifacts could potentially arise due to not using 3D spatial coherence. Tumor sensitive matching flow 6 was developed on CT scans to segment ovarian cancer metastases attached to liver and spleen, but ascites could be present away from those two organs.…”